com.springprompt/prompt-test

up checked 2026-11-11T15:37:57.435Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Spring Prompt

Publisher-provided description

The best prompt and the best model for the job, tested and improved by your coding agent.

Summary by lookupd

Tests and improves prompts across multiple models, reporting the best model, pass rates, costs and failures, with trained judges and…

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http prompt-test https://springprompt.com/mcp

Codex, remote (streamable-http)

codex mcp add prompt-test --url https://springprompt.com/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "prompt-test": {
      "url": "https://springprompt.com/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (16 tools)

Publisher-provided text

• get_started Where this account stands: credit, when free credit ends, prompts waiting to be tested, tests so far, and what to do next. Free.
• load_prompts Load prompts and their examples into the account for the person to review and run. Spends nothing. Returns a link to show them.
• run_loaded_prompt Test a prompt from load_prompts, using its cases and checks and drafting any that are missing. Spends credit, never more than max_spend_usd by estimate. Call ge
• test_prompt Start a test of one prompt across several models. Spends credit, never more than max_spend_usd by estimate. Returns at once with a test_id: call get_test for th
• get_test A test's status and, when done, what it found: the best model, each model's pass rate and cost, and sample failures.
• improve_prompt Rewrite a finished test's prompt from its failures and ratings, then test the new version on the same cases, checks and models. Spends credit.
• list_tests This account's recent prompt tests.
• list_models Models a test can use, with prices, and the credit left on this account.
• get_recommendation Which model a saved test's answers point to: the model to use, its pass rate and cost per 1,000 answers, the runner-up, when the test last ran, and whether pric
• list_recommendations The model to use for every saved test on this account, one entry per test, with what changed since each last ran. Runs nothing, free.
• rating_link A link that lets anyone rate a test's answers on their phone, with no account and the models hidden. Send it to whoever knows what good looks like. Anyone with
• train_judge Train a judge on a test's ratings. It's tested on answers it hasn't seen, and only kept if it beats always giving the commoner verdict. Spends a little credit.
• list_judges This account's trained judges, and how often each agreed with its rater.
• score_answers Score up to 50 answers with a trained judge: how likely the person it learned from is to call each one good, from 0 to 1. Spends a little credit.
• check_change Check a changed prompt or a different model against a saved test before it is merged. Runs the candidate on the test's cases and compares it with the test's sav
• get_check The state of a check started with check_change, and its verdict.

Details

• Version: 1.0.0
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 878 ms
• First indexed: 2026-11-06T09:17:11.812Z
• Last seen in registry: 2026-11-06T09:17:11.812Z
• Website: https://springprompt.com

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.springprompt/prompt-test.svg)](https://lookupd.com/servers/com.springprompt/prompt-test)

• 62092 servers
• Last crawl: 2026-11-11T17:38:11.606Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp